System and method for forecasting realized volatility via wavelets and non-linear dynamics
US8515850B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 29, 2011 |
| Grant date | Aug 20, 2013 |
| Priority date | — |
| Expiry date | Sep 3, 2031 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06Q40/06
- WIPO fieldIT methods for management
- WIPO sectorElectrical engineering
Abstract
The system and method described herein may be used to forecast realized volatility via wavelets and non-linear dynamics. In particular, a volatility time series that includes daily volatility values associated with a security may be decomposed into wavelets via multi-resolution analysis and dynamical properties associated with the individual wavelets may be analyzed to identify deterministic and non-deterministic wavelets and produce a volatility forecast derived from a fit computed on the deterministic wavelets. For example, the wavelets may be analyzed to discover time delay, Theiler, and embedding dimension values associated therewith, which may be used to project volatility values associated with each wavelet. The projected volatility values associated with each wavelet may then be summed to produce a volatility forecast associated with the security.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.